© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156050
    Prev
    Next
    INDEX
    Explanations

    not expressly

    np_acts-logits-general · gemini-2.5-flash-lite

    vibe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIN
    0.54
    Lengths
    0.48
    Dyn
    0.48
    DIA
    0.47
    D
    0.46
    viewer
    0.46
    Davies
    0.44
    SMITH
    0.44
     consuming
    0.43
    MOB
    0.42
    POSITIVE LOGITS
    నులు
    0.52
     for
    0.52
    सर्गिक
    0.52
     permitem
    0.51
     Nar
    0.51
     Governo
    0.51
    埶
    0.50
     右利き
    0.50
    انون
    0.50
     jugar
    0.50
    Activations Density 0.000%

    No Known Activations